SOURCE-LINKED INTELLIGENCE

Can You Trust Frozen Hematology Foundation Models under Acquisition Shift?

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Frozen hematology foundation-model (FM) embeddings reach near-saturated in-domain white-blood-cell (WBC) accuracy, but clinical deployment demands reliability across scanners, sites, stains and preparation pipelines. We audit 15 frozen encoders (hematology, pathology, and general vision) across four public single-cell acquisition domains along two axes: accuracy robustness and calibration. In-domain linear-probe macro-F1 is saturated (0.98-0.997), yet cross-dataset macro-F1 drops 34-72% and rankings re-order: DinoBloom-L, the in-domain best, falls to 10th of 15 on the most-shifted target (MLL2

Read original source ↗ Open in workspace

recordType

paper

region

Global